Computing at the Edge

The term “Intelligent Edge” is used in many ways, but perhaps the best way to think of it is as a place. The edge is where the action is. It’s a manufacturing floor, a building, a campus, a city, your house, a telecommunications outpost, a sports arena, or in other words, where the “things” are in the Internet of Things (IoT).  IoT data originates remotely, often from equipment at the edge, enabling immediate access to the data and affecting immediate control of “things”

 

The edge is “intelligent” because now there’s technology in these places that’s smart, connected, computational, and controlling.  Crucially, the Intelligent Edge provides analytics capabilities that were formerly confined to on-premises or cloud data centers.

 

The media and telecom industries face growing distribution pressures from increased video resolution, new formats, expanding bandwidth, and the need for better security and reliability. As a result, telecom service providers are placing sophisticated compute and control systems in businesses and homes. These distributed intelligent edges make the services more competitive and improve customer experiences.

 

Seven Reasons To Compute at the Edge

 

Edge computing can yield immediate insights from edge data at relatively low cost. Edge compute can be improved by shifting enterprise-class compute, storage, and management from the data center out to the edge. Organizations can leverage compute at the edge to:

 

  1. Minimize Latency: There are many applications that require immediate insight and control. For some mission-critical functions, compute must take place at the edge because any latency is intolerable.
  2. Reduce Bandwidth: Sending big data back and forth from things to the cloud, can consume enormous bandwidth. Edge computing is the easiest solution to this problem.
  3. Lower Cost: Even if bandwidth is available, it can be costly. Efficiency is an important element of any corporate IoT strategy.
  4. Reduce Threats: When you transfer data across the campus, state, country or ocean, it is simply more prone to attacks and breaches. Processing data at the edge can reduce security vulnerabilities.
  5. Avoid duplication: If all the data is collected and sent to the cloud, there will likely be some equipment duplication in memory, storage, networking equipment and software. If this duplication is not needed, then the associated increases in capital and operating expenditures are unwarranted.
  6. Improve reliability: Even without any nefarious activity from hackers, data can be corrupted on its own. Retries, drops and missed connections will plague edge-to-data-center communications.
  7. Maintain Compliance: Laws and corporate policies govern the remote transfer of data.

 

Reasons to compute at the edge

 

HPE Edgeline at the Intelligent Edge

 

The key to HPE’s IoT strategy is edge computing, combining OT and IT into one appliance. In June of 2016, HPE announced the EdgeLine 1000 and EdgeLine 4000 series of devices that allow more processing power to be deployed into the field near these connected devices that generate data.  Both devices accommodate the same M510 or M710x ProLiant cartridges used in HPE’s signature Moonshot Chassis, with room for one cartridge on the Edgeline 1000 appliance and four cartridges on the EL4000.  Both appliances have integrated wireless networking on the system.

 

HPE Edgeline E1000
HPE Edgeline E1000

 

 

HPE Edgeline E4000
HPE Edgeline E4000

 

In Las Vegas, Zunesis recently showcased AI-based image and video analytics applications that run on the Edgeline Devices (in tandem with the customers VMS platform).   The features and use cases are far reaching – just a few key features we showcased:

 

  • Immediate identification of key image elements, such as people or an abandoned bag.
  • Processing video nearer the point of capture, the camera, eliminating the need to transfer large amounts of video data into the datacenter or cloud, thus reducing bandwidth costs, accelerating reaction time and lowering risk of corruption or espionage.
  • Engagement geometry for smart video surveillance that can direct camera viewpoints and aggregate video data of a particular location
  • Long videos can be compressed into minutes by superimposing all moving elements over the same unchanging background. The technology is ideal for identifying popular items or routes.

 

Also exciting is HPE’s new Global IoT Innovation Lab – Asia Pacific (APAC), located at HPE’s APAC headquarters in Singapore, one of four globally that offers immersive Edge Experience Zones to demonstrate practical IoT use cases for industries such as oil & gas, manufacturing, engineering, healthcare, retail, smart cities and more.

 

For more details, check out this great article on the new Lab – http://www.techtradeasia.info/2018/02/hpe-opens-singapore-based-global-iot.html.

Scroll to Top